How do we take advantage of data within the context of learning and LMS?
Big data: extremely large dataset
it is typically used in data science field and learning analytics field, it refers to data that can be analyzed to reveal certain patterns related to human behaviors and interactions
it is data about how are people's actions online in certain platforms or face-to-face communication
Why big data as an emergent technology?
ishango bone from Congo : oldest mathematical tool
Fast forward to today where we have 149 zettabytes stored in data centers all over the world
So, we can say that we've been recording data for a very long time
The creation of data is not linear, its flunctuating:
up to 2003 -> we had half a zettabyte
in 2013 it took 2 days to create half a zettabyte of data
Examples of how data is used:
https://www.trends.google.com/trends/
There are different layers of data that you can observe
In the education field we categorize them in different levels:
Micro: data that is sampled quite frequently - within seconds e.g this could be mouse clicks or case behavior, they are used to identify learning processes
Meso (Medium): its data that is sampled less frequently - within minutes or hours or days - e.g posts of someone in a discussion forum, they are used to learn things about social interaction and cognitive functioning
Macro: its data that is related that is collected over a long period of time, within the education field is over multiple years, so this data can be sampled e.g once a month for years - this kind of data is used to inform early warning systems e.g attendance
The line between those levels is not too strict and depends on the field.
Big data enables us to refine theories at a granuylar level, meaning in a lot of details
Before you do data collection research you always do ethics statement:
Ethics statement: you justify the amount of data that you are collecting - stating why you are doing this
data rangling
Personalized learning
Improved decision-making
Enhanced pedagogical practices
Predictive analytics
Scalability and global impact
Real-time feedback
Data privacy and security
Bias and equity
Data interpretation and misuse/over-reliance
Infrastructure and access
Technical and analytical expertise
Data overload
the more you know about a person the more you can tailor the educational experience for them
also the more a teacher can adjust accordingly,
for predictive analytics - software that can predict e.g if a student is a risk of failing
Activity: Everyday big data scenarios
Conclusion: its not about different things necessarily, its about the same thing looking at it from different levels of granularity
What do we do with all this "big data"? in education
Learning analytics: its a field focused in understanding how we measure, collect, analyze and report data based on the context, with the aim to understand and optimize learning and the environments that it occurs
There are many models:
Clow's Learning Analytics Cycle
its a cyclical process - it loops on itself
it starts with the learners that we collect the data from
the students generate and we capture this data
there are different metrics that we have and we analyze this data that provide insights on how these learning processes are occuring
the loop closes with an intervention - for example with feedback on the students or teachers to inform and give feedback on how they can improve for the next cycle
Its important to consider that theory should be the core for the analytics
The role of theory is that it is the lens in which we view these interactions.
This is related to epistemological assumptions.
epistemology = the theory of knowledge - how do we know what we know
In Finland the major epistemological stance is social constructivism. It assumes that people learn through social interaction.
These assumptions influence how we collect, analyze, and how we provide interventions
The conclusion is: Context Matters - the data on its own doesnt give enough information
** That is why automated interventions are problematic because they lack of context
-> the systems that utilize the learning analytics. it is the operalization of learning analytics
They are digital platforms design to plan, deliver, track, and manage educational or training content.
Edtech in Finland is quite big. https://www.xedu.co/
The aim is to help improve learning outcomes, but the way that it is done is to try to make it more efficient, especially the administration part and making learning processes more efficient
There are different structures to do that, synchronous (chat, discussion) and asynchronous (the teacher uploading a material)
Within the educational field, LMS have been connected a lot to the concept of self-study or regulation of learning. They say that LMS help students learn on their own, to track their own progress, manage their own resources, study on their own time and overall become better learners. There is evidence both yper kai kata
Open question: To what extend LMS help with learning, and in which contexts hinder the learning?
It is often that teachers view LMS as an administrative tool rather than a tool for learning
-> LMS is an umbrella term but there are different variations.
e.g LMS, CMS, LCMS
Actionable feedback =
Affordances = possibilities that a technology offers
Key LMS affordances:
Interactivity
Collaboration
Acessibility
Scalability
Comparing TEAMS vs HOWSPACE from a student perspective
Microsoft Teams
Video calls
Private chats, better for communication
Accessibility on different devices
Synchronous and asynchronous collaboration
No gamification
Howspace
Interaction
Not accessible on phone
Only synchronous
AI features e.g summary, word clouds
Learning analytics
Language translation
Gamification elements